Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "I" and expressions of personal experience or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     impunity
    -0.86
     endif
    -0.72
     whichever
    -0.65
     indistinguishable
    -0.63
     margins
    -0.63
     inaction
    -0.63
     coercive
    -0.61
     srfAttach
    -0.61
    limits
    -0.60
     escal
    -0.60
    POSITIVE LOGITS
    've
    1.31
     awoke
    1.24
    'm
    1.22
     woke
    1.16
    stanbul
    1.10
     stumbled
    1.06
     recently
    1.01
     adore
    0.99
     arrived
    0.98
     LOVE
    0.97
    Act Density 0.215%

    No Known Activations